SavedAdd your journal

Journals / Business and Economics Research Journal / 2021 / Cilt: 12 - Sayı: 1

Predicting Direction of Stock Price Using Machine Learning Techniques: The Sample of Borsa Istanbul

Pay Senedi Fiyat Yönünün Makine Öğrenmesi Yöntemleri ile Tahmini: Borsa İstanbul Örneği

Barış AKSOY
Pages
89–110
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

According to the results of the analysis, general classification accuracy was achieved 98.05% for Artificial Neural Networks, 96.10% for Classification and Regression Tree, and 92.20% K-Nearest Neighbor Algorithm. “Net Profit Margin”, “Price/Earning”, “Profit Per Share”, “CDS Premium (3-month average)”, “Consumer Confidence Index” were found as important variables that divided the data into two in the creation of the Classification and Regression Tree (CART) analysis.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, stock price with the calculated next three-month average of five manufacturing industry companies in the Borsa İstanbul 30 Index and the Corporate Governance Index was predicted with the data of the 2010/3 and 2020/3 periods.
📊
Key Findings & Data:A 10-fold cross-validation method was used in all methods in the study.
💡
Conclusion & Impact:According to the results of the analysis, general classification accuracy was achieved 98.05% for Artificial Neural Networks, 96.10% for Classification and Regression Tree, and 92.20% K-Nearest Neighbor Algorithm. “Net Profit Margin”, “Price/Earning”, “Profit Per Share”, “CDS Premium (3-month average)”, “Consumer Confidence Index” were found as important variables that divided the data into two in the creation of the Classification and Regression Tree (CART) analysis.
🔬Design:Modeling & Simulation
📍Scope:2010 Verileri
⚙️Variables:Domain Parameters

Abstract

In this study, stock price with the calculated next three-month average of five manufacturing industry companies in the Borsa İstanbul 30 Index and the Corporate Governance Index was predicted with the data of the 2010/3 and 2020/3 periods. The dataset consisted of quarterly nine financial statements and five macroeconomic variables with a three-month average of the sample companies. Artificial Neural Networks, Classification and Regression Tree, and K- Nearest Neighbor Algorithm were used as prediction methods. A 10-fold cross-validation method was used in all methods in the study. In Artificial Neural Networks, Classification and Regression Tree analysis, the models that gave the best results in line with the given parameter ranges were obtained by using the determining the best parameters and performance criteria function. According to the results of the analysis, general classification accuracy was achieved 98.05% for Artificial Neural Networks, 96.10% for Classification and Regression Tree, and 92.20% K-Nearest Neighbor Algorithm. “Net Profit Margin”, “Price/Earning”, “Profit Per Share”, “CDS Premium (3-month average)”, “Consumer Confidence Index” were found as important variables that divided the data into two in the creation of the Classification and Regression Tree (CART) analysis. This result shows that the models used in this study can be incorporated into the models used by investors.

Özet

Bu çalışmada Borsa İstanbul 30 Endeksinde ve Kurumsal Yönetim Endeksinde bulunan beş imalat sanayi şirketinin 2010/3 ve 2020/3 dönemine ait verilerle üç ay sonraki ortalaması alınmış pay senedi fiyat yönü tahmin edilmiştir. Veri seti, örnek kapsamındaki şirketlerin üçer aylık dokuz mali tablo verisi ve üç aylık ortalaması alınmış beş makroekonomik değişkenden oluşmaktadır. Tahmin yöntemleri olarak Yapay Sinir Ağları, Sınıflandırma ve Regresyon Ağacı ile K- En Yakın Komşu Algoritması kullanılmıştır. Çalışmada kullanılan tüm yöntemlerde 10 katlı çapraz doğrulama yöntemi kullanılmıştır. Yapay Sinir Ağları ile Sınıflandırma ve Regresyon Ağacı analizlerinde en iyi parametrelerin ve performans kriterlerinin belirlenmesi fonksiyonu kullanılarak verilen parametre aralıkları doğrultusunda en iyi sonuç veren modeller elde edilmiştir. Analiz sonucuna göre pay senedi fiyat yününü Yapay Sinir Ağları %98,05, Sınıflandırma ve Regresyon Ağacı %96,10 ve K- En Yakın Komşu Algoritması %92,20 oranında genel sınıflandırma doğruluğu elde etmiştir. Sınıflandırma ve Regresyon Ağacının oluşturulmasında verileri ikiye bölen önemli değişkenler olarak “Net Kâr Marjı”, “Fiyat/Kazanç Oranı”, “Hisse Başına Kâr Oranı”, “CDS Primi (üç aylık ortalama)” ve “Tüketici Güven Endeksi” bulunmuştur. Bu bulgular, yatırımcıların bu çalışmada kullanılan modelleri kullanabileceklerini ve/veya hali hazırda kullanmış oldukları modellere dâhil edebileceklerini göstermektedir.

🔖

Cite This Article

AKSOY, B. (2021). Predicting Direction of Stock Price Using Machine Learning Techniques: The Sample of Borsa Istanbul. Business and Economics Research Journal, Cilt: 12 - Sayı: 1, 89–110. https://ajindex.com/articles/210728

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. Akay, E. Ç. (2018). Ekonometride yeni bir ufuk: Büyük veri ve makine öğrenmesi. Social Sciences Research Journal, 7(2), 41-53.
  2. Akcan, A., & Kartal, C. (2011). İMKB sigorta endeksini oluşturan şirketlerin hisse senedi fiyatlarının yapay sinir ağları ile tahmini. Muhasebe ve Finansman Dergisi, (51), 27-40.
  3. Akpınar, H. (2014). Data veri madenciliği veri analizi. İstanbul:
  4. Papatya Yayınları.
  5. Anbalagan, T., & Maheswari, S. U. (2015). Classification and prediction of stock market index based on fuzzy metagraph. Procedia Computer Science, (47), 214-221.
  6. Ataseven, B. (2013). Yapay sinir ağları ile öngörü modellemesi. Öneri Dergisi, 10(39), 101-115.
  7. Barak, S., & Modarres, M. (2015). Developing an approach to evaluate stocks by forecasting effective features with data mining methods. Expert Systems with Applications, (42), 1325-1339.
  8. Chen, Y., & Hao, Y. (2017). A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction. Expert Systems with Applications, (80), 340-355.
  9. Çelik, U., Akçetin, E., & Gök, M. (2017). Rapidminer ile veri madenciliği. İstanbul:
  10. Pusula Yayınları.
  11. Dhanalakshmi, S., & Subramanian, C. (2014). An analysis of data mining applications for fraud detection in securities market. International Journal of Data Mining Techniques and Applications, (3), 326-335.
  12. Elmas, Ç. (2018). Yapay zeka uygulamaları. Ankara:
  13. Seçkin Yayıncılık. Enke, D., & Thawornwong, S. (2005). The use of data mining and neural networks for forecasting stock market returns. Expert Systems with Applications, (29), 927-940.
  14. Gaganis, C. (2009). Classification techniques for the identification of falsified financial statements: A comparative analysis. Intelligent Systems in Accounting, Finance and Management, (16), 207-229.
  15. Huang, W., Nakamori, Y., & Wang, S.-Y. (2005). Forecasting stock market movement direction with support vector machine. Computers & Operations Research, (32), 2513-2522.
  16. Imandoust, S. B., & Bolandraftar, M. (2014). Forecasting the direction of stock market index movement using three data mining techniques: The case of Tehran Stock Exchange. Int. Journal of Engineering Research and Applications, 4(6), 106-117.
  17. Jardin, P. D. (2016). A Two-stage classification technique for bankruptcy prediction. European Journal of Operational Research, (254), 236-252.
  18. Kara, Y., Boyacioglu, M. A., & Baykan, Ö. K. (2011). Predicting direction of stock price index movement using artificial neural networks and support vector machines: The s